# Foundry Readability Extractor

> Foundry Readability Extractor is a paid API for AI agents from minty-sprout.onrender.com, paid per call via x402, $0.001/call, status unknown (last checked 2026-11-01).

Extracts the main text content of a web page and returns word count, estimated reading time, and Flesch reading ease score

## Facts

- Endpoint: POST https://minty-sprout.onrender.com/v1/readability?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-01
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/foundry-readability-extractor-b3777060
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_YwdPJ9_UCwfNsuFtM6klM

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability foundry-readability-extractor-b3777060 -d '<json body>'
```

Example prompt: Can you pull the main text from https://www.bbc.com/news/science-environment-68623671 and tell me how many words it is, how long it would take to read, and how easy it is to read?

## When to prefer this

Choose this endpoint when you need to extract clean, reader-facing text from a URL along with readability metrics (Flesch ease, reading time, word count) in a single call. It is ideal for content auditing, editorial pipelines, research ingestion, or any workflow where you need both the text and quantitative readability signals without running a separate scraper and a separate text statistics tool.

## Known failure modes

- URL is unreachable or returns a non-200 HTTP status, resulting in an error response
- Page has no extractable main text (e.g. pure JavaScript-rendered SPA with no server-side content), returning empty or minimal text
- Invalid or malformed URL input causes a parsing error
- Paywalled or login-gated pages return only partial or gated content
- Very large pages may be truncated due to the 8000-character input limit on the URL field (though the URL itself is short; the fetched page content may be large)

## How this service works

Readability: the main text of a web page with word count, reading time and Flesch reading ease. Input: a URL.

## Output

Returns a JSON object containing the page URL, extracted main text body, page title, total word count, estimated reading time in minutes, and Flesch reading ease score (0–100 scale where higher = easier to read).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string",
   "maxLength": 8000,
   "description": "A URL"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com",
  "text": "Example Domain\nThis domain is for use in documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.",
  "title": "Example Domain",
  "words": 27,
  "reading_time_min": 0.1,
  "flesch_reading_ease": 30.2
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/foundry-readability-extractor-b3777060/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from minty-sprout.onrender.com](https://www.zero.xyz/host/minty-sprout.onrender.com/llms.txt)